get('Core.LexerImpl'); } $needs_tracking = $config->get('Core.MaintainLineNumbers') || $config->get('Core.CollectErrors'); $inst = null; if (is_object($lexer)) { $inst = $lexer; } else { if (is_null($lexer)) { do { // auto-detection algorithm if ($needs_tracking) { $lexer = 'DirectLex'; break; } if (class_exists('DOMDocument') && method_exists('DOMDocument', 'loadHTML') && !extension_loaded('domxml') ) { // check for DOM support, because while it's part of the // core, it can be disabled compile time. Also, the PECL // domxml extension overrides the default DOM, and is evil // and nasty and we shan't bother to support it $lexer = 'DOMLex'; } else { $lexer = 'DirectLex'; } } while (0); } // do..while so we can break // instantiate recognized string names switch ($lexer) { case 'DOMLex': $inst = new HTMLPurifier_Lexer_DOMLex(); break; case 'DirectLex': $inst = new HTMLPurifier_Lexer_DirectLex(); break; case 'PH5P': $inst = new HTMLPurifier_Lexer_PH5P(); break; default: throw new HTMLPurifier_Exception( "Cannot instantiate unrecognized Lexer type " . htmlspecialchars($lexer) ); } } if (!$inst) { throw new HTMLPurifier_Exception('No lexer was instantiated'); } // once PHP DOM implements native line numbers, or we // hack out something using XSLT, remove this stipulation if ($needs_tracking && !$inst->tracksLineNumbers) { throw new HTMLPurifier_Exception( 'Cannot use lexer that does not support line numbers with ' . 'Core.MaintainLineNumbers or Core.CollectErrors (use DirectLex instead)' ); } return $inst; } // -- CONVENIENCE MEMBERS --------------------------------------------- public function __construct() { $this->_entity_parser = new HTMLPurifier_EntityParser(); } /** * Most common entity to raw value conversion table for special entities. * @type array */ protected $_special_entity2str = array( '"' => '"', '&' => '&', '<' => '<', '>' => '>', ''' => "'", ''' => "'", ''' => "'" ); /** * Parses special entities into the proper characters. * * This string will translate escaped versions of the special characters * into the correct ones. * * @warning * You should be able to treat the output of this function as * completely parsed, but that's only because all other entities should * have been handled previously in substituteNonSpecialEntities() * * @param string $string String character data to be parsed. * @return string Parsed character data. */ public function parseData($string) { // following functions require at least one character if ($string === '') { return ''; } // subtracts amps that cannot possibly be escaped $num_amp = substr_count($string, '&') - substr_count($string, '& ') - ($string[strlen($string) - 1] === '&' ? 1 : 0); if (!$num_amp) { return $string; } // abort if no entities $num_esc_amp = substr_count($string, '&'); $string = strtr($string, $this->_special_entity2str); // code duplication for sake of optimization, see above $num_amp_2 = substr_count($string, '&') - substr_count($string, '& ') - ($string[strlen($string) - 1] === '&' ? 1 : 0); if ($num_amp_2 <= $num_esc_amp) { return $string; } // hmm... now we have some uncommon entities. Use the callback. $string = $this->_entity_parser->substituteSpecialEntities($string); return $string; } /** * Lexes an HTML string into tokens. * @param $string String HTML. * @param HTMLPurifier_Config $config * @param HTMLPurifier_Context $context * @return HTMLPurifier_Token[] array representation of HTML. */ public function tokenizeHTML($string, $config, $context) { trigger_error('Call to abstract class', E_USER_ERROR); } /** * Translates CDATA sections into regular sections (through escaping). * @param string $string HTML string to process. * @return string HTML with CDATA sections escaped. */ protected static function escapeCDATA($string) { return preg_replace_callback( '//s', array('HTMLPurifier_Lexer', 'CDATACallback'), $string ); } /** * Special CDATA case that is especially convoluted for